EP0014850A1 - Dispositif pour étendre le jeu normal de makro-instructions dans un système de traitement d'information - Google Patents

Dispositif pour étendre le jeu normal de makro-instructions dans un système de traitement d'information Download PDF

Info

Publication number
EP0014850A1
EP0014850A1 EP80100323A EP80100323A EP0014850A1 EP 0014850 A1 EP0014850 A1 EP 0014850A1 EP 80100323 A EP80100323 A EP 80100323A EP 80100323 A EP80100323 A EP 80100323A EP 0014850 A1 EP0014850 A1 EP 0014850A1
Authority
EP
European Patent Office
Prior art keywords
pla
programmable logic
microprocessor
data
output
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
EP80100323A
Other languages
German (de)
English (en)
Other versions
EP0014850B1 (fr
Inventor
Joseph Carl Logue
Wei-Wha Wu
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by International Business Machines Corp filed Critical International Business Machines Corp
Publication of EP0014850A1 publication Critical patent/EP0014850A1/fr
Application granted granted Critical
Publication of EP0014850B1 publication Critical patent/EP0014850B1/fr
Expired legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00—Digital computers in general; Data processing equipment in general
    • G06F15/76—Architectures of general purpose stored program computers
    • G06F15/78—Architectures of general purpose stored program computers comprising a single central processing unit
    • G06F15/7839—Architectures of general purpose stored program computers comprising a single central processing unit with memory
    • G06F15/7864—Architectures of general purpose stored program computers comprising a single central processing unit with memory on more than one IC chip
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/22—Microcontrol or microprogram arrangements
    • G06F9/223—Execution means for microinstructions irrespective of the microinstruction function, e.g. decoding of microinstructions and nanoinstructions; timing of microinstructions; programmable logic arrays; delays and fan-out problems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/22—Microcontrol or microprogram arrangements
    • G06F9/226—Microinstruction function, e.g. input/output microinstruction; diagnostic microinstruction; microinstruction format

Definitions

  • the invention relates to a device for expanding the function of a data processing system according to the preamble of claim 1.
  • PLAs In the context of electronic data processing systems, programmable logic arrangements, or PLAs for short, play a role in the execution of instructions, as described, for example, in US Pat. Nos. 3,949,370, 3,962,683 and 4,074,351.
  • the PLAs used in the subject matter of these patents are arranged in two hierarchical levels, one level generating a PLA with an instruction or address and all other PLAs responding to those instructions or addresses by executing a subroutine at an underlying level. More specifically, the PLAs described in the cited patents provide sequential control for a central processing unit.
  • the module works autonomously as a selectively programmed mini processor with a differently specialized or personalized operation and repertoire.
  • a PLA with a memory
  • it has the disadvantage of comparatively high costs, since the PLA required for this has to be relatively large.
  • the invention is therefore based on the object of specifying a functionally expandable data processing system which manages with smaller and thus less expensive programmable logic arrangements without loss of speed.
  • the advantage of system expandability and functional flexibility is therefore achieved by the combination of at least one programmable logic arrangement with a microprocessor, the costs (due to the use of commercially available microprocessors and programmable logic arrangements) in no way increasing and the processing speed decreasing.
  • the functional expansion of the data processing system is possible without structural changes to the microprocessor itself, so that advantages also result from this.
  • FIG. 1 shows a block diagram of an embodiment of the present invention.
  • the system components of the modular data processing device communicate with one another via a standard system bus, consisting of a control bus 1, an address bus 2 and a data bus 3.
  • This bus structure is a main feature of commercially available microprocessors, which simplifies both the circuit structure and programming for microcomputer applications.
  • the programmable logic arrangements (PLAs) 4, 5 and 6 serve as functional execution units (FEUs). They are part of the system modules and are constructed in such a way that they can be plugged directly onto the system busbars in order to be able to execute more highly structured instructions.
  • FEUs functional execution units
  • the microprocessor (MPU) 7, the read-only memory (ROM) 8 and the read-write memory (RAM) 9 are standard components of commercially available microcomputers, such as the 6800 from Motorola or 8080 from Intel. Although the number of components in the 6800 and 8080 microcomputers are different, they have the same bus structure, namely 10 control lines, 10 address lines and an 8 bit wide bidirectional (two-way) data bus.
  • Figure 2 shows a block diagram of the-6800 processor unit. It should be noted in this regard that two or more programmable logic devices which have the same architecture can be connected in parallel in order to expand the functional capabilities, such as, for example, the number of macro instructions, the peripheral input / output connections or the number of address bits for direct memory access (DMA).
  • DMA direct memory access
  • the architecture of the circuit implementation of the invention can be reflected in three exemplary embodiments, which are designated MP, PIO and DMA.
  • the MP configuration (PLA 4 in Fig. 1) performs highly structured macro functions such as subroutines, multiplications, conversion tables, special algorithms, counter / timer functions, parity detection / generation, cyclic redundancy checks (CRC), query sequences, ping-pong buffer controls, comparison - / branching functions and the same.
  • the PIO configuration (PLA 5) performs the interface function for the peripheral devices 10 with the microprocessor 7 and performs input / output functions, such as SERDES functions (series / parallel conversion of data configurations), serves as a data format generator, as a time interval decoder, as a data detector, as a transition pulse generator, as a modem (modulator / demodulator) and carries out processes such as adding, inserting, removing.
  • the DMA configuration (PLA 6) transfers data blocks directly between the main memory (RAM 9) and external devices (not shown). Exemplary embodiments are explained below which show how the programmable logic arrangements 4, 5 and 6 connect to the microprocessor 7 in a program-controlled manner.
  • MICROPROCESSOR CONFIGURATION MP: The normal operation of the programmable logic device 4 controlled by the microprocessor 7 requires that certain control and timing signals are present and that the peripheral circuits of the programmable logic device 4 are divided in such a way that they effectively perform special functions , either combinatorial or sequential.
  • 3 shows, as a block diagram, the layout of the programmable logic arrangement as a microprocessor configuration MP.
  • the two-sided data bus 3 transmits data from and to the microprocessor 7.
  • the data output drivers 11 are designed as drivers which can assume three states and which are controlled by the TSC line 12. When the drivers are turned on via line 12, their output assumes a high impedance state. In this way, it is possible to isolate the data stored in the output latch circuits 13 (OL) from the data bus.
  • the data input ver latch circuits 14 (IL) are latch circuits (D-type or polarity holder) which can be switched through gate circuits and which serve as input buffer memories and are controlled by the ILC line 15. If the control signal on line 15 takes a high level, then the input is not turned on. This prevents data from connected PLAs from being processed.
  • Eight inputs are used to address a macro instruction that represents a group of bit patterns (or product terms) that perform a special function. It is essential that the address itself serves as the operation code of a macro instruction.
  • eight input latch circuits 14 connected to the address bus 2 serve as instruction registers. The number of different addressable macro commands now depends on how the eight inputs are connected to address bus 2.
  • 4 shows the memory allocation of a typical microprocessor system. This layout shows the storage locations to which the various system components are assigned. For example, address bits A15 and A14 are linked to the address inputs of PLA 4.
  • the programmable logic arrangement PLA 4 will always be connected to the microprocessor MPU (7) via the data bus 3. Since two bits are used to allocate the PL A 4, the remaining 6 bits allow the use of a maximum of 64 macro commands (OP codes). The number of macro instructions could be even higher if two or more macro instructions would always occur in sequence. These macro instructions can be applied to multiple PLAs, such as PLA 4, be distributed. However, it should be mentioned here that because of the memory allocation technique shown in FIG. 4, the use of only a few memory addresses is useless. If every bit of an available memory address is to be used, then a 16-wire address bus must also be used or external decoding must be provided.
  • the reset input 16 in FIG. 3 resets PLA 4 and switches it on again from the switched-off state, which could have resulted from a fault in the power supply or an initial switch-on sequence of the processor. If the input line 16 carries a high level signal, then all register and latch circuits in the OR arrangement 17 of the PLA 4 are cleared, and the holding line 23 also carries a high level signal.
  • the read / write input (R / W) 21 is coupled to the R / W control line 21 of the microprocessor 7 in FIG. 2.
  • the read / write input 21 tells the PLA 4 whether the microprocessor 7 is in a read (high level) or write (low level) state.
  • the read / write input is also connected to the ILC input 15 in order to control the data flow, either in the direction of the microprocessor 7 or in the direction of the PLA 4.
  • the ILC line 15 carries a high level signal that blocks the inputs to the input latch circuits 14 through gate circuits. These gates are open when a write cycle is carried out.
  • the switch-on input (DBE) 22 of the data bus is connected to the DBE control line 22 in Fig. 2 of the microprocessor, which is in the normal Operation is controlled by the phase 2 clock signal ( ⁇ 2).
  • the signal on the DBE control line 22 indicates to the PLA 4 that there is valid data on the data bus 3 and the execution of a macro instruction can take place.
  • the stop output line 23 is connected to the stop control line 23 in FIG. 2 of the microprocessor 7.
  • the processor 7 stops operating and the processor stops at the end of an instruction. Since the microprocessor 7 and the PLA 4 operate synchronously, the stop signal puts the microprocessor in a waiting state until the PLA 4 has finished its task.
  • the PLA 4 may take more than one cycle to execute a macro instruction if it is a sequential function. However, if the macro instruction is a combinatorial one, it only takes one cycle to execute and the stop signal 23 is not required.
  • the input lines 24 and output lines 25 are used only for testing purposes. Since all the latch circuits in the OR array 17, which are the accumulators 26, the macro-instruction register (MIR) 27 and the output latch circuits are connected in series 13, so as to form a shift register, the P can rüfarian into the input end and the result data of the test on A are pushed usgabeausgang.
  • MIR macro-instruction register
  • Two-bit division is not required for the control and address input portion of the AND array 26 because it is used strictly for decoding and not for performing logic operations.
  • the inputs mentioned are connected to phase splitters 27.
  • the data Bus line part 28 and the feedback part 29 of the AND arrangement have a two-bit division to improve the logic function.
  • the AND arrangement which has 100 product terms, has an 80 x 100 bit organization. For executing instructions of a higher programming language than one of several applications, the number of product terms becomes more important than the number of inputs.
  • the feedback part is divided into logic (30) and macro selection fields 31.
  • Logic field 30, which is 16 bits wide, is used to perform combinatorial and sequential functions.
  • the macro selection field 31, on the other hand is 4 bits wide and is used to select (a total of 16) macro instructions.
  • the return part of the OR arrangement 17 is divided into the accumulator field 26 and the macro instruction register field 27.
  • the accumulator field with a width of 16 bits has two accumulators A and B which have a two-bit division, for example AO, BO, A1, B1, A2, B2 etc.
  • the macro instruction register field MIR serves the same purpose of selecting macro instructions as the address bus 2. However, for performing sequential functions (one macro instruction at a time), the hakro instruction register field 27 speeds up execution because the processor does not have to transmit a macro instruction (OP CODE) to the programmable logic array via the address bus 2.
  • the output part 13 of the arrangement uses JK flip-flops (latches) as an output buffer (with 11 bists).
  • PERIPHERAL INPUT / OUTPUT (PIO) CONFIGURATION In the PIO 5 configuration according to FIG. 5, input and output connections have been added, to which certain control signals are assigned. Peripheral inputs 32 and peripheral outputs 33 are connected to peripheral devices (not shown), such as a keyboard, display unit, printer, magnetic memory (tape or disk), or groups of sensors and actuators. During normal operation, these input / output connections are used for transmission of data (one bit or two bits) between the external devices and the microprocessor 7 (Fig. 1) via the programmable ogikan remedy L5.
  • the "input ready" signal on line 34 comes from a peripheral device.
  • This signal signals the programmable logic arrangement 5 (PLA 5) that its data are available at the peripheral input.
  • the input acknowledge signal on line 35 is transmitted to the peripheral device. It reports to this device that the data has been received.
  • the output request line 36 reports to the PLA 5 that the peripheral device is requesting data.
  • the ready-to-issue line 37 reports to the peripheral device that the data is available on the peripheral output circuits of the PL A 5.
  • the interrupt request output (IRQ) 38 requests the generation of a circuit controlled interrupt sequence in the machine.
  • the operational flow diagram of the circuit controlled interrupt sequence is shown in FIG. 6. Before the processor recognizes this request, it waits until the current instruction has been completely executed.
  • the machine starts the interruption sequence, when the interrupt mask bit in the condition code register of the microprocessor 7 is not set (47 in Fig. 6).
  • the contents of index registers 39 and 40 (in FIG. 2), program counters 40 and 42, accumulators 43 and 44 and condition code register 35 are then stored in the stack (48 in FIG. 6).
  • the microprocessor 7 will respond to the interrupt request by setting the interrupt mask bit (49 in Fig. 6) so that no further interruptions can occur.
  • the program counter is loaded with a 16-bit address (50 in Fig. 6) which is the contents of the memory locations FFF 8 and FFF 9 and which points to a vector address. An address loaded in these memory locations causes the microprocessor 7 to branch to a subroutine in the memory.
  • the stop line 23 must have a high signal level so that interruptions are recognized as such. External interrupt priority circuits can be connected to the machine if more than one IRQ line is used.
  • the peripheral circuits of the AND arrangement 51 shown in FIG. 5 have input latch circuits 52, phase splitters 53 and "two on four" decoders 54 and 55 so that they correspond to the corresponding assemblies of the AND arrangement 26 of the programmable logic arrangement (MP) 4 3, which has already been explained, are similar.
  • the input latch circuit 52 consists of D flip-flops and serves as an input buffer. It is necessary because the signals from the peripheral devices are not stable. The pulse width can either be too narrow or due to Prel len with gaps. The input latch circuit therefore allows the input signal to have a minimum pulse width (availability time).
  • the AND arrangement 41 has a 96 x 86 bit or a 112 x 80 bit organization, which depends on whether the input connection has 8 or 16 lines.
  • the peripheral circuitry of OR array 56 includes accumulators 57 (A and B), a macro instruction register (MIR) 58, an output latch circuit 59, chip output driver (O CD ) 60, and a TSC controller 61 for the three states that the drivers can assume .
  • the peripheral circuits mentioned are similar to those of the OR arrangement 17 of the programmable logic arrangement 4 in FIG. 3, which has also already been explained above.
  • the OR arrangement 56 has an 84 x 80 bit or 100 x 80 bit organization, depending on the number of connection lines that the output connection has.
  • DMA direct memory access
  • main memory main memory
  • peripheral device not shown
  • DMA technology allows the data to be transferred to and from the main memory 9 without the microprocessor 7 being involved. In this way the throughput, ie the speed of the microprocessor 7 is improved.
  • 7 shows a programmable logic arrangement 6 which has an architecture according to the DMA configuration.
  • a 16 bit address bus 62 at the output of the PLA 6 as well requires the following control signals: bus line available (BA) 63, valid memory address (VMA) 64 and read / write (R / W) 67.
  • the input line 63 for the bus line available signal comes from the microprocessor 7 and is used to grant direct memory access (DMA) . It goes high when the microprocessor 7 stops and all three-state lines are high impedance, indicating that DMA transfers can begin.
  • the valid memory address (VMA) output line 64 comes from a gate circuit with an open collector at output 65 of the programmable logic arrangement. It has a high signal level when the microprocessor 7 is stopped. This signal is galvanically OR-linked to the VMA line 66 of the microprocessor and is used to actuate the main memory 9 during a DMA transfer.
  • the read / write (R / W) output line 67 carries a command signal which is used to control the direction of transfer in a DMA operation. This output line is connected to a tri-state output driver controlled by the TSC2 line 70.
  • the R / W output line 67 at the PLA 6 input is connected inversely to the BA line 63 in FIG. 7 via a gate circuit. This means that if the signal on BA line 63 goes high, then the R / W output signal on line 67 has no effect on the corresponding column in AND arrangement 68 of PLA 6.
  • the PLA outputs 62, 69 and 70 which are connected to the address bus 2, the data bus 3 and the R / W output line 67 of the micro processor connected, three - are state outputs that are in high impedance state when the signal on BA line 63 goes low and the microprocessor 7 controls the address, data and control bus lines.
  • the stop signal 23 at the output serves as a DMA request, which commands the microprocessor 7 to stop and sets its three-state lines to the high-impedance state.
  • the operations taking place here and the timing of DMA transfers by stopping the microprocessor 7 are known per se.
  • the rest of the input and output lines as well as the peripheral circuitry of the PLA 6 are similar to those already described in connection with the MP and input / output configurations.
  • PROGRAM CONTROL Within each PLA there are groups of bit patterns or product terms called macro instructions that perform special functions. Each M akrobeutton an operation code (OPCODE) is associated with a high-quality instruction being) compared by the AND array through the address bus or ⁇ decoded. If there is a match, the macro instruction is executed and the result is buffered in the accumulators or in the output latches, depending on the function to be performed. From there, the result must either be transferred back to the processor or to the external device.
  • OPCODE operation code
  • Each PLA is a high-speed function execution unit for executing higher instructions, which are normally executed sequentially by subroutines within a processor.
  • the control of the data transfer between the microprocessor 7 and the PLAs 4, 5 and 6 in FIG. 1 can be carried out with the aid of the following instructions, for example using a Motorola 6800 microprocessor.
  • Example 1 It is assumed that a byte of the binary data which is to be converted in the 6800 (MPU 7) accumulator A by means of a table in the PLA 4 of FIG. 1 and is to be stored back in the accumulator B of the MPU 7.
  • the program flow for this operation is shown in Fig. 8. If the program counter (PC) 41 and 42 in FIG. 2 detects a JMP instruction in the memory location n of the ROM 8 (read-only memory), it jumps to the subroutine location k after the execution of the JMP instruction. At the same time, the location of the next main instruction (n + 2) is saved in the stack.
  • PC program counter
  • the MPU 7 then starts the execution of the subroutine (subroutine) by calling STAA, CNC (conversion instruction, coded as 10000001; see FIG. 3) and then executes it.
  • the associated timing is shown in Fig. 9A.
  • the contents of the accumulator A is transferred to the PLA via the data bus 3, namely via the CNV1 table of the AND arrangement 26, and the result obtained is stored in the output latch circuits 13 in FIG. 3.
  • both the stop signal 23 and the three-state drivers 11 of the PLA 4 are switched on.
  • the stop signal is then switched off when the second conversion cycle (CNV2) has ended.
  • the three state drivers 11 remain in the high impedance state.
  • the STAA opcode (1 byte) is stored in the instruction register of the microprocessor 7 and the CNV opcode (2 bytes) is stored in an intermediate register within the microprocessor 7.
  • the STAA operation code and the DNV operation code are decoded in the decoding circuits of the microprocessor 7 and in the AND arrangement 26 of the PLA 4, respectively. If the stop signal is activated, the microprocessor 7 is brought into the waiting state until the stop signal is switched off. Thereafter, the program counter is incremented and the microprocessor 7 starts the fetching of the next instructions, LDAB and P1OLO (PLA 4 output interlock circuit open instruction, coded as 10000010; cf.
  • Fig. 3 When the PIOLO instruction is executed, the TSC signal on line 12 assumes a low level. This returns the outputs of the output latch circuits 13 from the high impedance state to the normal state, so that the contents of the output latch circuits 13 become available on the data bus 3. The timing of this read cycle is shown in Fig. 9B. After this cycle is completed, the contents of the output latch circuits 13 are loaded into the accumulator B and an RTS (subroutine return) operation takes place. The program counter PC then sets itself to position N + 2 of the next main instruction a.
  • the stack pointer S P points to the previous storage location m, as shown in FIG. 8.
  • Example 2 It is assumed here that data of a peripheral device 10 in FIG. 1 (for example a sensor) are to be converted, the CNV table in the PLA 5 of FIG. 5 being used and the result for a comparison and a vote is to be transferred to the PLA 4 using the CMP & AJS macro command.
  • the coordinated data are then temporarily stored in the accumulator A of the microprocessor 7 until the peripheral device requests them, for example in order to actuate a mechanical switch which is connected to the peripheral device.
  • the figures 6 and 10 show the flow of this special operation.
  • the data arrives at the CNV table of the AND array 51 when the data from the peripheral device 10 is ready and the input ready signal is on line 36.
  • the result of this operation is stored in the output latch circuits 59.
  • signal IRQ on line 36 assumes a low level.
  • the microprocessor senses the IRQ signal, it enters a circuit controlled interrupt sequence shown in FIG. 6.
  • the program counter PC jumps to the interrupt routine point k, which is shown in FIG. 10.
  • the microprocessor 7 fetches and executes the instructions LDAA and P20LO (PLA 5 output lock circuit open instruction, coded as 10000100; see FIG. 5).
  • the function of the P20LO instruction is the same as the PIOLO instruction that was explained earlier. After execution the microprocessor loads the contents of the PLA 5 output latch circuits 59 into the accumulator A.
  • FIG 11A shows the timing conditions for the control lines, PLA 5 and microprocessor 7.
  • the program counter reaches memory location K + 1
  • microprocessor 7 calls the STAA and CMP & AJS instructions and executes them. This causes the content of the accumulator A to be transferred to the PLA 4 and processed by the macro instruction CMP & AJS (operation code 10000011; see FIG. 3). The result is then stored in the PLA 4 output latch circuits 13. This data is transferred back to the accumulator when the microprocessor 7 executes the next instructions LDAA and P10LO.
  • execution of the interrupt return instruction ends the interrupt routine and transfers control of the microprocessor 7 to the main program.
  • the request for data by the peripheral device can occur either before or after the execution of the RTI instruction. If the request occurs prior to the execution of the RTI instruction by leveling the output request line 36 (from the peripheral device 10), thereby activating the IRQ2 signal on line 71 in Fig. 5, then the microprocessor 7 becomes the Do not acknowledge the next interruption until the first one has been fully operated. If, however, the IRQ1 signal is recognized by the microprocessor 7, then the interrupt priority circuits control the microprocessor to the corresponding memory locations in the read-only memory 8 in order to obtain the vector, as shown in FIG. 10.
  • the next step of the microprocessor is to fetch and execute the STAA and DBPO (data bus-to-peripheral-output instruction, encoded as 10000101; see Fig. 5).
  • STAA and DBPO data bus-to-peripheral-output instruction, encoded as 10000101; see Fig. 5.
  • the content of the accumulator A reaches the peripheral output connection via the data bus 3.
  • the ready-to-dispense line 37 is activated.
  • Fig. 11 shows the timing of the data flow from the microprocessor 7 to the peripheral device 10. It should be mentioned here that during normal transfer operations the input ready (34) and the output request (36) signals in Fig. 5 (both from the peripheral Device) occur after the ready-to-go (37) and input-confirm (35) lines both take high levels from the PLA 4.
  • Fig. 12 shows the entire data flow between the peripheral device and the microprocessor 7 via the PLAs 4 and 5. Also shown are the instructions which are used to control the data flow.
  • Example 3 It is assumed here that a data block is to be transferred from the main memory 9 of FIG. 1 to a visual display device (not shown) by defining the first memory location M1 and the last memory location M2 of the data block.
  • an input device such as a keyboard
  • the display device is connected to the output of the peripheral device to the PLA 5 shown in Fig. 1 during the DMA operation by the PLA 6 in Fig. 7).
  • the processor When the keyboard signals a data transfer, the processor starts to operate an interrupt routine.
  • the addresses M1 and M2 are first loaded into the accumulators A and B of the PLA 6, which is shown in FIG. 7.
  • the DBPO macro instruction establishes a connection path for the transfer of memory data from the bus 3 to the peripheral output 33 (CRT) in FIG. 5.
  • the INCMP macro instruction is functionally the combination of a counter, a comparator and a link of data from the PLA 6 accumulator A to the address bus output 62 in Fig. 7.
  • a macro instruction is executed after the BA signal (DMA granted) on line 63 assumes a high level value, then the counter starts from M1 to M2 and stops there. In the meantime, a whole series of memory addresses are generated. These are then used to retrieve the data and transfer them from the main memory to the CRT data display device via the DBPO connection path in the PLA 5.
  • Halt signal (DMA request) on line 23 in Fig. 7 may be asynchronous with the currently executing instruction, this results in a variable time delay from the signal falling in level to the rising signal BA (DMA granted) Line 63 in Fig. 7.
  • the maximum time delay occurs when the hold line 23 assumes a low level in the first cycle of a long instruction, which long instruction may be a programmed interrupt (SWI) that Is 12 cycles long.
  • SWI programmed interrupt
  • a cycle is added which is required for the address of the microprocessor 7, the data and R / W signals, for the setting to a high level value. This delay must be taken into account when DMA transfers are running.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Hardware Design (AREA)
  • Microcomputers (AREA)
  • Executing Machine-Instructions (AREA)
  • Bus Control (AREA)
  • Advance Control (AREA)
EP80100323A 1979-02-26 1980-01-23 Dispositif pour étendre le jeu normal de makro-instructions dans un système de traitement d'information Expired EP0014850B1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US15505 1979-02-26
US06/015,505 US4268908A (en) 1979-02-26 1979-02-26 Modular macroprocessing system comprising a microprocessor and an extendable number of programmed logic arrays

Publications (2)

Publication Number Publication Date
EP0014850A1 true EP0014850A1 (fr) 1980-09-03
EP0014850B1 EP0014850B1 (fr) 1984-10-31

Family

ID=21771796

Family Applications (1)

Application Number Title Priority Date Filing Date
EP80100323A Expired EP0014850B1 (fr) 1979-02-26 1980-01-23 Dispositif pour étendre le jeu normal de makro-instructions dans un système de traitement d'information

Country Status (9)

Country Link
US (1) US4268908A (fr)
EP (1) EP0014850B1 (fr)
JP (1) JPS55115143A (fr)
AU (1) AU537064B2 (fr)
BR (1) BR8001032A (fr)
CA (1) CA1136768A (fr)
DE (1) DE3069537D1 (fr)
ES (1) ES488841A1 (fr)
IT (1) IT1148853B (fr)

Families Citing this family (26)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4482953A (en) * 1980-05-30 1984-11-13 Fairchild Camera & Instrument Corporation Computer with console addressable PLA storing control microcode and microinstructions for self-test of internal registers and ALU
US4467409A (en) * 1980-08-05 1984-08-21 Burroughs Corporation Flexible computer architecture using arrays of standardized microprocessors customized for pipeline and parallel operations
US4399516A (en) * 1981-02-10 1983-08-16 Bell Telephone Laboratories, Incorporated Stored-program control machine
USRE32858E (en) * 1981-02-10 1989-02-07 American Telephone And Telegraph Company, At&T Bell Laboratories Stored-program control machine
US4583193A (en) * 1982-02-22 1986-04-15 International Business Machines Corp. Integrated circuit mechanism for coupling multiple programmable logic arrays to a common bus
US4575794A (en) * 1982-02-22 1986-03-11 International Business Machines Corp. Clocking mechanism for multiple overlapped dynamic programmable logic arrays used in a digital control unit
US4447813A (en) * 1982-06-04 1984-05-08 Control Resources Corporation Programmable bus for the control of electronic apparatus
DE3233343A1 (de) * 1982-09-08 1984-03-08 Siemens AG, 1000 Berlin und 8000 München Prozessoreinheit eines rechners
JPS6065342A (ja) * 1983-09-20 1985-04-15 Fujitsu Ltd マイクロコンピユ−タ
USRE34363E (en) * 1984-03-12 1993-08-31 Xilinx, Inc. Configurable electrical circuit having configurable logic elements and configurable interconnects
GB2161001B (en) * 1984-06-25 1988-09-01 Rational Distributed microcode address apparatus for computer
US4670835A (en) * 1984-10-19 1987-06-02 Honeywell Information Systems Inc. Distributed control store word architecture
DE3508984A1 (de) * 1985-03-13 1986-09-18 Siemens AG, 1000 Berlin und 8000 München Verarbeitungseinheit fuer befehle, bestehend aus ausfuehrungseinheit und zusatzausfuehrungseinheit
US4789957A (en) * 1986-03-28 1988-12-06 Texas Instruments Incorporated Status output for a bit slice ALU
JP2845433B2 (ja) * 1987-09-07 1999-01-13 日本電気株式会社 集積回路装置
FR2633407B1 (fr) * 1988-06-27 1990-11-02 Crouzet Sa Dispositif programmable de commande de relais
GB9223226D0 (en) 1992-11-05 1992-12-16 Algotronix Ltd Improved configurable cellular array (cal ii)
US5455525A (en) * 1993-12-06 1995-10-03 Intelligent Logic Systems, Inc. Hierarchically-structured programmable logic array and system for interconnecting logic elements in the logic array
JPH07168803A (ja) * 1994-07-25 1995-07-04 Seiko Epson Corp 半導体装置
JPH07168802A (ja) * 1994-07-25 1995-07-04 Seiko Epson Corp 半導体装置
US5893040A (en) * 1996-05-15 1999-04-06 The Boeing Company Method and apparatus for automatically providing jet engine thrust ratings to avionic systems
US6085317A (en) * 1997-08-15 2000-07-04 Altera Corporation Reconfigurable computer architecture using programmable logic devices
US7035948B1 (en) * 2001-03-19 2006-04-25 Transdimension, Inc. System and method for USB controllers
US6511867B2 (en) * 2001-06-30 2003-01-28 Ovonyx, Inc. Utilizing atomic layer deposition for programmable device
WO2004032256A1 (fr) * 2002-08-21 2004-04-15 Ovonyx, Inc. Utilisation de depot en couche atomique pour dispositif programmable
US7577726B1 (en) * 2002-02-07 2009-08-18 Cisco Technology, Inc. Method for updating a hardware configuration of a networked communications device

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3681761A (en) * 1969-05-02 1972-08-01 Ibm Electronic data processing system with plural independent control units

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3962683A (en) * 1971-08-31 1976-06-08 Max Brown CPU programmable control system
US3916169A (en) * 1973-09-13 1975-10-28 Texas Instruments Inc Calculator system having a precharged virtual ground memory
US3983538A (en) * 1974-05-01 1976-09-28 International Business Machines Corporation Universal LSI array logic modules with integral storage array and variable autonomous sequencing
US3949370A (en) * 1974-06-06 1976-04-06 National Semiconductor Corporation Programmable logic array control section for data processing system
US3959774A (en) * 1974-07-25 1976-05-25 California Institute Of Technology Processor which sequences externally of a central processor
US4074351A (en) * 1974-12-02 1978-02-14 Texas Instruments Incorporated Variable function programmed calculator
US3988717A (en) * 1975-08-06 1976-10-26 Litton Systems, Inc. General purpose computer or logic chip and system
US4040032A (en) * 1976-02-27 1977-08-02 Data General Corporation Peripheral device controller for a data processing system

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US3681761A (en) * 1969-05-02 1972-08-01 Ibm Electronic data processing system with plural independent control units

Also Published As

Publication number Publication date
ES488841A1 (es) 1980-09-16
US4268908A (en) 1981-05-19
CA1136768A (fr) 1982-11-30
BR8001032A (pt) 1980-10-29
EP0014850B1 (fr) 1984-10-31
DE3069537D1 (en) 1984-12-06
AU537064B2 (en) 1984-06-07
JPS55115143A (en) 1980-09-04
JPS6229815B2 (fr) 1987-06-29
IT1148853B (it) 1986-12-03
AU5453980A (en) 1980-09-04
IT8019451A0 (it) 1980-01-25

Similar Documents

Publication Publication Date Title
EP0014850B1 (fr) Dispositif pour étendre le jeu normal de makro-instructions dans un système de traitement d'information
DE2856483C2 (fr)
DE2713400C3 (de) Numerisches Steuersystem für Bearbeitungszentren
EP0952520B1 (fr) Dispositif d'exécution de programmes tolerante aux pannes
DE1774296B2 (de) Restruktuierbare Steuereinheit für elektronische Digitalrechner
DE2641741A1 (de) Rechnersystem aus mehreren miteinander verbundenen und zusammenwirkenden einzelrechnern
DE3606650A1 (de) Hardware logik-simulator
DE1524209A1 (de) Leitwerk fuer eine Rechenanlage
DE2948285A1 (de) Adressensteuersystem fuer softwaresimulation
DE2855673C2 (fr)
DE2404146A1 (de) Digitales, hierarchisch in wenigstens drei hierarchie-stufen aufgebautes speichersystem
DE2019444A1 (de) Datenverarbeitungsanlage
DE2755616A1 (de) Asymmetrischer multiprozessor
DE4005042C2 (de) Mehrrechnersystem zur Durchführung von Bewegungssteuerungen
DE4010311A1 (de) Datenprozessor
DE3809831A1 (de) Digitalrechner mit befehlsmodusumwandlung
EP0130269B1 (fr) Commande à programme mémorisé
WO1996016366A1 (fr) Configuration a unites maitresses et asservies
DE19983975B3 (de) Programmierbares Steuersystem und Rücksetz-Steuerverfahren für das programmierbare Steuersystem
DE1499191B2 (de) Elektronische einrichtung fuer eine datenverarbeitungsanlage
EP0350016B1 (fr) Procédé et dispositif pour dupliquer le contenu de supports d'informations
DE2938929A1 (de) Dv-system
DE3426902A1 (de) Schaltungsanordnung zum konfigurieren von peripherieeinheiten in einer datenverarbeitungsanlage
DE2856768C2 (de) Prioritäts-Vektor-Unterbrechungsvorrichtung
EP0273070B1 (fr) Dispositif et méthode d'extension du jeu d'instructions et des fonctions d'un calculateur

Legal Events

Date Code Title Description
PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

AK Designated contracting states

Designated state(s): BE CH DE FR GB NL SE

17P Request for examination filed

Effective date: 19801007

GRAA (expected) grant

Free format text: ORIGINAL CODE: 0009210

AK Designated contracting states

Designated state(s): BE CH DE FR GB NL SE

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: NL

Effective date: 19841031

REF Corresponds to:

Ref document number: 3069537

Country of ref document: DE

Date of ref document: 19841206

ET Fr: translation filed
NLV1 Nl: lapsed or annulled due to failure to fulfill the requirements of art. 29p and 29m of the patents act
PLBE No opposition filed within time limit

Free format text: ORIGINAL CODE: 0009261

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT

26N No opposition filed
PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: SE

Effective date: 19860124

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: GB

Payment date: 19891231

Year of fee payment: 11

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: DE

Payment date: 19900209

Year of fee payment: 11

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: CH

Payment date: 19900427

Year of fee payment: 11

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: FR

Payment date: 19901227

Year of fee payment: 12

PGFP Annual fee paid to national office [announced via postgrant information from national office to epo]

Ref country code: BE

Payment date: 19910114

Year of fee payment: 12

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: GB

Effective date: 19910123

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: CH

Effective date: 19910131

GBPC Gb: european patent ceased through non-payment of renewal fee
REG Reference to a national code

Ref country code: CH

Ref legal event code: PL

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: DE

Effective date: 19911001

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: BE

Effective date: 19920131

BERE Be: lapsed

Owner name: INTERNATIONAL BUSINESS MACHINES CORP.

Effective date: 19920131

PG25 Lapsed in a contracting state [announced via postgrant information from national office to epo]

Ref country code: FR

Effective date: 19920930

REG Reference to a national code

Ref country code: FR

Ref legal event code: ST

EUG Se: european patent has lapsed

Ref document number: 80100323.7

Effective date: 19861023